pith. sign in

Integrity report for Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders

A machine-verified record of the checks Pith has run against this paper: detector runs, findings, signed bundle events, and canonical identifiers.

arXiv:2605.27354 · pith:2026:37G2J3II3D2P2EPFJ2GB33D2VA

0Critical
0Advisory
6Detectors run
2026-05-29Last checked

Paper page arXiv integrity.json bundle.json

Detector runs

claim_evidence completed v1.0.0 · findings 0 · 2026-05-29 05:45:09.940904+00:00
external_links completed v1.0.0 · findings 0 · 2026-05-27 17:31:37.729464+00:00
shingle_duplication skipped v0.1.0 · findings 0 · 2026-05-27 05:49:58.231583+00:00
citation_quote_validity skipped v0.1.0 · findings 0 · 2026-05-27 03:50:18.587904+00:00
ai_meta_artifact skipped v1.0.0 · findings 0 · 2026-05-27 02:34:12.006096+00:00
cited_work_retraction completed v1.0.0 · findings 0 · 2026-05-27 02:23:35.902775+00:00

Findings

No public integrity findings for this paper.

Signed record

The machine-readable record for this paper lives at /pith/37G2J3II/integrity.json. Pith Number bundles also include signed pith.integrity.v1 events where a Pith Number exists.